Error analysis and the role of morphology
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Error analysis and the role of morphology. / Bollmann, Marcel; Søgaard, Anders.
EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics, 2021. p. 1887-1900.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Error analysis and the role of morphology
AU - Bollmann, Marcel
AU - Søgaard, Anders
N1 - Publisher Copyright: © 2021 Association for Computational Linguistics
PY - 2021
Y1 - 2021
N2 - We evaluate two common conjectures in error analysis of NLP models: (i) Morphology is predictive of errors; and (ii) the importance of morphology increases with the morphological complexity of a language. We show across four different tasks and up to 57 languages that of these conjectures, somewhat surprisingly, only (i) is true. Using morphological features does improve error prediction across tasks; however, this effect is less pronounced with morphologically complex languages. We speculate this is because morphology is more discriminative in morphologically simple languages. Across all four tasks, case and gender are the morphological features most predictive of error.
AB - We evaluate two common conjectures in error analysis of NLP models: (i) Morphology is predictive of errors; and (ii) the importance of morphology increases with the morphological complexity of a language. We show across four different tasks and up to 57 languages that of these conjectures, somewhat surprisingly, only (i) is true. Using morphological features does improve error prediction across tasks; however, this effect is less pronounced with morphologically complex languages. We speculate this is because morphology is more discriminative in morphologically simple languages. Across all four tasks, case and gender are the morphological features most predictive of error.
M3 - Article in proceedings
AN - SCOPUS:85107267336
SP - 1887
EP - 1900
BT - EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
PB - Association for Computational Linguistics
T2 - 16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021
Y2 - 19 April 2021 through 23 April 2021
ER -
ID: 283136052